Paper search
Search scientific papers with a natural-language query and optional filters for authors, categories, and date bounds.
Firecrawl Research
Firecrawl Research is a research-specific index for finding papers, reading paper passages, exploring related work, and searching research-related GitHub repos. It is built for AI agents and developers working with scientific and engineering research.
Overview
Firecrawl Research is a research-focused index for scientific and engineering work. It helps agents search papers, inspect paper metadata, read supporting passages from a paper, discover related work, and search research-related GitHub repositories.
The documentation positions it as a purpose-built workflow for agents that need to move from a paper query to evidence, context, and adjacent work without leaving the Firecrawl ecosystem. It is exposed through API endpoints, the Firecrawl CLI, and the MCP server.
Capabilities
Paper metadata lookup
Open a canonical paper record or a source-specific ID to inspect metadata such as IDs, title, abstract, and score.
Passage reading
Ask a question against a paper and retrieve the most relevant full-text passages to verify methods, datasets, constraints, or results.
Related-paper discovery
Expand from one or more seed papers to similar papers, citing papers, or referenced papers using semantic expansion and ranking.
GitHub research search
Search research-related GitHub history and README content for implementation notes, bugs, and design discussions.
Common use cases
Literature discovery
Use keyword or natural-language searches to find papers by topic, method, benchmark, author, or category, then narrow results with metadata filters.
Paper verification
Inspect canonical metadata, source IDs, and abstracts when you need a dependable paper record for downstream analysis or citation workflows.
Evidence checking
Read the most relevant passages from a paper to confirm whether it actually contains a method, dataset, constraint, or result before using it in research.
Related-work expansion
Start from one or more seed papers and expand to related work, citing papers, or references to build a broader research map.
Research-to-code tracing
Search GitHub history and README files for implementation notes, bugs, and design discussions that connect papers to code.
Pros and Cons
Pros
- Supports topic, method, benchmark, author, and category-style paper discovery.
- Returns canonical paper IDs and source IDs for citation and follow-up access.
- Can read targeted passages from a paper instead of relying only on abstracts.
- Supports structural expansion to similar papers, citers, and references.
- Can be accessed through multiple surfaces, including API endpoints, CLI, and MCP.
Cons
- The pricing page is not available in the supplied sources, so plan structure and limits are not documented here.
- The GitHub-search section is only partially shown in the provided text, so its exact scope is not fully visible from these sources.
FAQ
What does Firecrawl Research do?
It is a research-specific toolset for searching papers, inspecting paper metadata, reading relevant full-text passages, finding related papers, and searching research-related GitHub repos.
How do you access the Research Index from an agent?
The documentation recommends using the Firecrawl CLI or MCP Server, together with the dedicated research skill, to give an agent access to the Research Index.
What tasks can the Research Index handle?
The documented workflows include searching papers, inspecting a paper by canonical paperId or source-specific primaryId, reading passages for a question, finding related papers, and searching GitHub history.
Do you need an API key to start using it?
The source text says no API key is needed to get started for research search and related endpoints, and that adding an API key provides higher rate limits.
Quick Facts
- Category
- Research index / developer tool
- Product type
- Documentation-backed API and agent toolset
- Primary surfaces
- API, CLI, MCP server
- Source domain
- docs.firecrawl.dev
- Primary users
- AI agents and developers working with papers and research repos
Alternative a Firecrawl Research
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
Hype
Hype is a web tool for finding trending YouTube topics by category, time range, and scoring mode. It helps creators spot emerging ideas, inspect source videos, and decide what to cover next.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
Ably Chat
Ably Chat is a chat API platform for building custom realtime chat applications. It supports room-based messaging, typing indicators, presence, reactions, and message updates, with usage-based pricing options for different deployment stages.
Manta AI
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.